© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32284
    Prev
    Next
    INDEX
    Explanations

    years and centuries

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens—years, dates, and other digit sequences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Recently
    -1.12
     Recently
    -0.99
    Just
    -0.90
     lately
    -0.88
     make
    -0.86
    bido
    -0.86
     recently
    -0.84
     थी
    -0.84
    Then
    -0.84
    Currently
    -0.84
    POSITIVE LOGITS
     XVIII
    1.16
     eighteenth
    1.10
     seventeenth
    1.03
     XVII
    0.94
    ITHER
    0.91
     DISPLAY
    0.91
     Unii
    0.90
    HOO
    0.84
     sixteenth
    0.84
    Sébastien
    0.82
    Activations Density 0.090%

    No Known Activations